test

src/app.ts

@@ -0,0 +1,158 @@
+const MINIMAX_API_KEY = process.env.MINIMAX_API_KEY;
+if (!MINIMAX_API_KEY) {
+  throw new Error("MINIMAX_API_KEY environment variable is required");
+}
+
+interface VoiceSetting {
+  voice_id: string;
+  speed: number;
+  vol: number;
+  pitch: number;
+  emotion?: string;
+}
+
+interface AudioSetting {
+  sample_rate: number;
+  bitrate: number;
+  format: "mp3" | "wav" | "ogg" | "aac";
+  channel: number;
+}
+
+interface PronunciationDictEntry {
+  text: string;
+  pronunciation: string;
+}
+
+interface MiniMaxTTSRequest {
+  model: string;
+  text: string;
+  stream?: boolean;
+  voice_setting: VoiceSetting;
+  audio_setting: AudioSetting;
+  pronunciation_dict?: {
+    tone: PronunciationDictEntry[];
+  };
+  subtitle_enable?: boolean;
+}
+
+interface MiniMaxTTSResponse {
+  code: number;
+  desc: string;
+  data?: {
+    audio?: string;
+    audio_file?: string;
+    subtitle_info?: string;
+  };
+}
+
+const BASE_URL = "https://api.minimaxi.com/v1/t2a_v2";
+
+export async function textToSpeech(
+  request: MiniMaxTTSRequest
+): Promise<Buffer> {
+  const response = await fetch(BASE_URL, {
+    method: "POST",
+    headers: {
+      Authorization: `Bearer ${MINIMAX_API_KEY}`,
+      "Content-Type": "application/json",
+    },
+    body: JSON.stringify(request),
+  });
+
+  if (!response.ok) {
+    const body = await response.text();
+    throw new Error(`MiniMax API error: ${response.status} ${response.statusText} - ${body}`);
+  }
+
+  const result = (await response.json()) as MiniMaxTTSResponse;
+
+  if (result.code && result.code !== 0) {
+    throw new Error(`MiniMax API error: ${result.code} - ${result.desc}`);
+  }
+
+  if (!result.data?.audio && !result.data?.audio_file) {
+    throw new Error("No audio data returned");
+  }
+
+  const audioHex = result.data.audio || result.data.audio_file!;
+  const audioBuffer = Buffer.from(audioHex, "hex");
+  return audioBuffer;
+}
+
+export async function textToSpeechStream(
+  request: MiniMaxTTSRequest,
+  onChunk: (chunk: Buffer) => void
+): Promise<void> {
+  const response = await fetch(BASE_URL, {
+    method: "POST",
+    headers: {
+      Authorization: `Bearer ${MINIMAX_API_KEY}`,
+      "Content-Type": "application/json",
+    },
+    body: JSON.stringify({ ...request, stream: true }),
+  });
+
+  if (!response.ok) {
+    throw new Error(`MiniMax API error: ${response.status} ${response.statusText}`);
+  }
+
+  if (!response.body) {
+    throw new Error("No response body");
+  }
+
+  const reader = response.body.getReader();
+
+  while (true) {
+    const { done, value } = await reader.read();
+    if (done) break;
+    onChunk(Buffer.from(value));
+  }
+}
+
+export const VOICE_IDS = {
+  male_qn_qingse: "male-qn-qingse",
+  female_tianmei: "female-tianmei",
+  male_baixian: "male-baixian",
+  female_aicheng: "female-aicheng",
+  male_yunyang: "male-yunyang",
+  female_xiaomo: "female-xiaomo",
+} as const;
+
+export type VoiceId = (typeof VOICE_IDS)[keyof typeof VOICE_IDS];
+
+export const EMOTIONS = {
+  neutral: "neutral",
+  happy: "happy",
+  sad: "sad",
+  angry: "angry",
+  fearful: "fearful",
+  disgust: "disgust",
+  surprised: "surprised",
+} as const;
+
+export type Emotion = (typeof EMOTIONS)[keyof typeof EMOTIONS];
+
+// Usage example:
+// async function example() {
+//   const audio = await textToSpeech({
+//     model: "speech-2.8-hd",
+//     text: "今天是不是很开心呀(laughs)，当然了！",
+//     stream: false,
+//     voice_setting: {
+//       voice_id: VOICE_IDS.male_qn_qingse,
+//       speed: 1,
+//       vol: 1,
+//       pitch: 0,
+//       emotion: EMOTIONS.happy,
+//     },
+//     audio_setting: {
+//       sample_rate: 32000,
+//       bitrate: 128000,
+//       format: "mp3",
+//       channel: 1,
+//     },
+//   });
+//
+//   // Save audio to file (Node.js)
+//   await import("fs/promises").then(fs => fs.writeFile("output.mp3", audio));
+// }